Molecular Engineering of Superplasticizers for Metakaolin‐Portland Cement Blends with Hierarchical Machine Learning

Menon, Aditya Krishna; Childs, Christopher M.; Póczos, Barnabás; Washburn, Newell R.; Kurtis, Kimberly E.

doi:10.1002/adts.201800164

Cited by 18 publications

(10 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The outcome of this work is that the trained HML algorithm predictions were used to guide the synthesis of the random copolymer with a molar composition of 50% styrene sulfonate (SS), 25% methacrylic acid (MAA), and 25% poly(ethylene glycol) methacrylate (PMA). The results are depicted in Figure 3 [28]. It had three unexpected attributes:…”

Section: Latent Variables Using Hmlmentioning

confidence: 99%

See 1 more Smart Citation

Advancing cement-based materials design through data science approaches

Rios¹,

Childs²,

Smith³

et al. 2021

RILEM Tech Lett

View full text Add to dashboard Cite

The massive scale of concrete construction constrains the raw materials’ feedstocks that can be considered – requiring both universal abundance but also economical and energy-efficient processing. While significant improvements– from more efficient cement and concrete production to increased service life – have been realized over the past decades through traditional research paradigms, non-incremental innovations are necessary now to meet increasingly urgent needs, at a time when innovations in materials create even greater complexity. Data science is revolutionizing the rate of discovery and accelerating the rate of innovation for material systems. This review addresses machine learning and other data analytical techniques which utilize various forms of variable representation for cementitious systems. These techniques include those guided by physicochemical and cheminformatics approaches to chemical admixture design, use of materials informatics to develop process-structure-property linkages for quantifying increased service life, and change-point detection for assessing pozzolanicity in candidate supplementary cementitious materials (SCMs). These latent variables, coupled with approaches to dimensionality reduction driven both algorithmically as well as through domain knowledge, provide robust feature representation for cement-based materials and allow for more accurate models and greater generalization capability, resulting in a powerful design tool for infrastructure materials.

show abstract

Section: Latent Variables Using Hmlmentioning

confidence: 99%

“…These form the middle layer. Note that in this study [28], the cement, mineral, and water variables were all held fixed and the only free variables were those of polymer chemistry, as shown in Figure 2.…”

Section: Latent Variables Using Hmlmentioning

confidence: 99%

Advancing cement-based materials design through data science approaches

Rios¹,

Childs²,

Smith³

et al. 2021

RILEM Tech Lett

View full text Add to dashboard Cite

show abstract

“…Metakaolin, a kind of high-performance mineral admixture, is formed by calcination of kaolin at 600~800 °C. Metakaolin is rich in raw materials, has similar activity to silica fume, and has a better effect on improving the properties of cement-based materials [ 17 , 18 , 19 , 20 ].…”

Section: Introductionmentioning

confidence: 99%

Prediction of the Compressive Strength for Cement-Based Materials with Metakaolin Based on the Hybrid Machine Learning Method

et al. 2022

View full text Add to dashboard Cite

Cement-based materials are widely used in construction engineering because of their excellent properties. With the continuous improvement of the functional requirements of building infrastructure, the performance requirements of cement-based materials are becoming higher and higher. As an important property of cement-based materials, compressive strength is of great significance to its research. In this study, a Random Forests (RF) and Firefly Algorithm (FA) hybrid machine learning model was proposed to predict the compressive strength of metakaolin cement-based materials. The database containing five input parameters (cement grade, water to binder ratio, cement-sand ratio, metakaolin to binder ratio, and superplasticizer) based on 361 samples was employed for the prediction. In this model, FA was used to optimize the hyperparameters, and RF was used to predict the compressive strength of metakaolin cement-based materials. The reliability of the hybrid model was verified by comparing the predicted and actual values of the dataset. The importance of five variables was also evaluated, and the results showed the cement grade has the greatest influence on the compressive strength of metakaolin cement-based materials, followed by the water-binder ratio.

show abstract

“…Machine learning methods are gradually applied to the evaluation and prediction of the mechanical performance of cement materials [22][23][24][25][26][27][28][29][30][31][32]. e punching shear capacity of steel fiber reinforced concrete slabs was predicted by using the sequential piecewise multiple linear regression and artificial neural network [33].…”

Section: Introductionmentioning

confidence: 99%

Predicting the Permeability of Pervious Concrete Based on the Beetle Antennae Search Algorithm and Random Forest Model

Huang

Duan

Zhang

et al. 2020

Advances in Civil Engineering

View full text Add to dashboard Cite

Pervious concrete is an environmentally friendly material that improves water permeability, skid resistance, and sound absorption characteristics. Permeability is the most important functional performance for the pervious concrete while limited studies have been conducted to predict permeability based on mix-design parameters. This study proposed a method to combine the beetle antennae search (BAS) and random forest (RF) algorithm to predict the permeability of pervious concrete. Based on the 36 samples designed in the laboratory and 4 key influencing variables, the permeability of pervious concrete can be obtained by varying mix-design parameters by RF. BAS algorithm was used to tune the hyperparameters of RF, which were then verified by the so-called 10-fold cross-validation. Furthermore, the model to combine the BAS and RF was validated by the correlation parameters. The results showed that the hyperparameters of RF can be tuned by the BAS efficiently; the BAS can combine the conventional RF algorithm to construct the evolved model to predict the permeability of pervious concrete; the cement/aggregate ratio was the most significant variable to determine the permeability, followed by the coarse aggregate proportions.

show abstract

Molecular Engineering of Superplasticizers for Metakaolin‐Portland Cement Blends with Hierarchical Machine Learning

Cited by 18 publications

References 47 publications

Advancing cement-based materials design through data science approaches

Advancing cement-based materials design through data science approaches

Prediction of the Compressive Strength for Cement-Based Materials with Metakaolin Based on the Hybrid Machine Learning Method

Predicting the Permeability of Pervious Concrete Based on the Beetle Antennae Search Algorithm and Random Forest Model

Contact Info

Product

Resources

About